A method, apparatus, device, and medium for predicting vehicle collision risks.

Abstract

This invention discloses a vehicle collision risk prediction method, apparatus, device, and medium. The method includes: determining the radius of the vehicle's trajectory when it is detected that the vehicle is traveling on a curved road; determining the radius of curvature of the potential collision object on the curved road based on the number of radar electromagnetic wave echoes received sequentially, wherein the center positions of the trajectories and the radius of curvature of the potential collision object are the same; calculating the difference between the trajectories and the radius of curvature of the potential collision object on the curved road; and predicting the collision risk between the vehicle and the potential collision object based on the relationship between the absolute value of the difference and the width of the lane where the vehicle is located. By adopting the above technical solution, the safety of vehicles traveling on curved roads is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of autonomous driving technology, and more specifically, to a method, apparatus, device, and medium for predicting vehicle collision risks. Background Technology

[0002] Driving autonomous vehicles on curved roads (such as ramps) is a crucial component of the autonomous driving field. This requires advanced sensors and perception systems that acquire three-dimensional information about the surrounding environment, identifying key elements such as obstacles, lane markings, and traffic signs to provide decision-making support for the autonomous driving system.

[0003] However, due to the unique characteristics of curved roads, vehicles on curves may not be able to perceive objects at greater distances. If there are stationary obstacles or oncoming vehicles using the same lane to overtake ahead, there is a risk of collision if the vehicle brakes suddenly after spotting the obstacle or oncoming vehicle due to insufficient braking distance. Therefore, there is an urgent need for a beyond-line-of-sight obstacle recognition solution for curve collision warning to ensure vehicle safety when driving on curved roads. Summary of the Invention

[0004] This invention provides a vehicle collision risk prediction method, apparatus, device, and medium to predict the collision risk between a vehicle and an obstacle in a curved road section with beyond visual range.

[0005] The specific technical solution is as follows:

[0006] In a first aspect, embodiments of the present invention provide a vehicle collision risk prediction method, the method comprising:

[0007] When the current vehicle is detected to be traveling on a curved road section, determine the radius of the current vehicle's travel trajectory;

[0008] Based on the number of radar electromagnetic wave echoes received successively, if it is determined that there is a potential collision object in front of the current vehicle, the radius of curvature of the trajectory of the potential collision object in the curved road section is determined. The radius of the driving trajectory is the same as the center position of the circle corresponding to the radius of curvature of the trajectory of the potential collision object in the curved road section.

[0009] Calculate the difference between the radius of the driving trajectory and the radius of curvature of the trajectory of the potential collision object on the curved road section, and predict the collision risk between the current vehicle and the potential collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

[0010] As demonstrated by the above scheme, in scenarios where vehicles are traveling on curved roads, the principle of secondary reflection of radar waves allows for the identification of potential collision obstacles ahead of the vehicle, even beyond visual range. By analyzing the absolute value of the difference between the vehicle's trajectory radius and the radius of curvature of the potential collision obstacle on the curved road, and the width of the lane in which the vehicle is currently positioned, a collision risk can be predicted. This allows for proactive measures such as slowing down or braking to mitigate the collision and ensure safety while driving on curves.

[0011] Optionally, determine the radius of the current vehicle's trajectory, including:

[0012] Determine the current vehicle's trajectory point position information based on its own coordinate system;

[0013] Based on the location information of each trajectory point, the equation of the driving trajectory curve is obtained by fitting each trajectory point.

[0014] The radius of the current vehicle's trajectory is determined based on the equation of the trajectory curve.

[0015] Optionally, based on the location information of each trajectory point, the equation of the driving trajectory curve is fitted to each trajectory point, including:

[0016] The equation of the current vehicle's driving trajectory curve is obtained by fitting each trajectory point with an Nth-order polynomial.

[0017] Accordingly, the radius of the current vehicle's trajectory is determined based on the trajectory curve equation, including:

[0018] Determine the curvature information of the driving trajectory curve equation, and calculate the current vehicle's driving trajectory radius based on the geometric relationship between the curvature information and the radius of curvature.

[0019] Optionally, determining the radius of curvature of the trajectory of the potential collision object on the curved road segment includes:

[0020] Based on the first time difference from when the vehicle-mounted radar emits electromagnetic waves to when it first receives the radar electromagnetic wave echo, and the second time difference when it receives the electromagnetic wave echo for the second time, the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the object at risk of collision is calculated.

[0021] Based on the trigonometric function relationship between the reflection distance, the radius of curvature of the trajectory of the potential collision object on the curved road section, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated.

[0022] Optionally, the radius of curvature of the roadside guardrail is calculated as follows:

[0023] The grounding point of the roadside guardrail is determined based on the coordinate information of the vehicle coordinate system;

[0024] The coordinate information of each roadside guardrail grounding point is fitted based on an Nth-order polynomial to obtain the trajectory equation of the roadside guardrail grounding point.

[0025] Determine the curvature information of the trajectory equation of the roadside guardrail's ground contact point, and calculate the curvature radius of the roadside guardrail based on the geometric relationship between the curvature information and the curvature radius. The curvature radius of the roadside guardrail is at the same center position as the radius of the driving trajectory.

[0026] As can be seen from the above technical solution, by using the principle of secondary reflection of radar waves, it is possible to predict whether there is a collision risk ahead of the curve when the distance is beyond visual range. This allows for advance driving strategies to avoid risks and ensure the safety of vehicles when driving on curved roads.

[0027] Optionally, based on the trigonometric relationship between the reflection distance, the radius of curvature of the trajectory of the potential collision object on the curved section, and the radius of curvature of the roadside guardrail, the radius of curvature of the potential collision object on the curved section is calculated, including:

[0028] Based on the sine theorem, calculate the angle between the first line segment from the risk collision object to the target reflection point and the second line segment from the target reflection point to the center of the curvature circle of the roadside guardrail;

[0029] Based on the law of cosines, and according to the angle between the first and second line segments, the reflection distance, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated.

[0030] Optionally, based on the relationship between the absolute value of the difference and the width of the lane where the vehicle is currently located, the collision risk between the current vehicle and the potential collision object can be predicted, including:

[0031] If the absolute value of the difference is greater than or equal to the width of the lane where the current vehicle is located, then it is determined that there is no risk of collision between the current vehicle and the object of potential collision.

[0032] If the absolute value of the difference is less than the width of the lane where the current vehicle is located, then it is determined that there is a collision risk between the current vehicle and the object at risk of collision.

[0033] After determining that there is a collision risk between the current vehicle and the potential collision object, the method provided in this embodiment of the invention further includes:

[0034] Control the current vehicle to slow down.

[0035] Secondly, embodiments of the present invention also provide a vehicle collision risk prediction device, the device comprising:

[0036] The vehicle driving radius determination module is configured to determine the driving trajectory radius of the current vehicle when it is detected that the current vehicle is driving on a curved road section;

[0037] The collision risk object trajectory radius determination module is configured to determine the radius of curvature of the trajectory of the risk object on the curved road section based on the number of radar electromagnetic wave echoes received successively, when it is determined that there is a risk collision object in front of the current vehicle. The radius of the current vehicle's trajectory is the same as the center position of the circle corresponding to the radius of curvature of the risk collision object's trajectory on the curved road section.

[0038] The collision risk prediction module is configured to calculate the difference between the radius of the driving trajectory and the radius of curvature of the trajectory of the potential collision object on a curved road section, and predict the collision risk between the current vehicle and the potential collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

[0039] Optionally, the vehicle driving radius determination module includes:

[0040] The trajectory point location determination unit is configured to determine the trajectory point location information of the current vehicle based on the vehicle coordinate system;

[0041] The driving trajectory curve fitting unit is configured to fit each trajectory point according to the position information of each trajectory point to obtain the driving trajectory curve equation;

[0042] The trajectory radius determination unit is configured to determine the current vehicle's trajectory radius based on the trajectory curve equation.

[0043] Optionally, the driving trajectory curve fitting unit is specifically configured as follows:

[0044] The equation of the current vehicle's driving trajectory curve is obtained by fitting each trajectory point with an Nth-order polynomial.

[0045] Accordingly, the driving trajectory radius determination unit is specifically configured as follows:

[0046] Determine the curvature information of the driving trajectory curve equation, and calculate the current vehicle's driving trajectory radius based on the geometric relationship between the curvature information and the radius of curvature.

[0047] Optional, the collision risk object trajectory radius determination module includes:

[0048] The reflection distance calculation unit is configured to calculate the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the object at risk of collision, based on the first time difference from the first time the radar emits electromagnetic waves to the first time the radar electromagnetic wave echo is received, and the second time difference from the second time the electromagnetic wave echo is received.

[0049] The collision risk object curvature radius determination unit is configured to calculate the radius of curvature of the collision risk object's trajectory on the curved road section based on the trigonometric function relationship between the reflection distance, the radius of curvature of the trajectory of the risk object on the curved road section, and the radius of curvature of the roadside guardrail.

[0050] Optionally, the radius of curvature of the roadside guardrail is calculated as follows:

[0051] The grounding point of the roadside guardrail is determined based on the coordinate information of the vehicle coordinate system;

[0052] The coordinate information of each roadside guardrail grounding point is fitted based on an Nth-order polynomial to obtain the trajectory equation of the roadside guardrail grounding point.

[0053] Determine the curvature information of the trajectory equation of the roadside guardrail's ground contact point, and calculate the curvature radius of the roadside guardrail based on the geometric relationship between the curvature information and the curvature radius. The curvature radius of the roadside guardrail is at the same center position as the radius of the driving trajectory.

[0054] Optionally, the collision risk object curvature radius determination unit is specifically configured as follows:

[0055] Based on the sine theorem, calculate the angle between the first line segment from the risk collision object to the target reflection point and the second line segment from the target reflection point to the center of the curvature circle of the roadside guardrail;

[0056] Based on the law of cosines, and according to the angle between the first and second line segments, the reflection distance, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated.

[0057] Optional, the collision risk prediction module is specifically configured as follows:

[0058] If the absolute value of the difference is greater than or equal to the width of the lane where the current vehicle is located, then it is determined that there is no risk of collision between the current vehicle and the object of potential collision.

[0059] If the absolute value of the difference is less than the width of the lane where the current vehicle is located, then it is determined that there is a collision risk between the current vehicle and the object at risk of collision.

[0060] Optionally, the apparatus provided in this embodiment of the invention further includes:

[0061] After determining that there is a collision risk between the current vehicle and the potential collision object, the current vehicle is controlled to slow down.

[0062] Thirdly, embodiments of the present invention provide a computer device, the computer device comprising:

[0063] At least one processor is coupled to a memory, the memory storing a program or instructions that run on the processor, the program or instructions which, when executed by the processor, implement the vehicle collision risk prediction method as provided in any embodiment of the present invention.

[0064] Fourthly, embodiments of the present invention provide a readable storage medium having a program or instructions stored thereon, which, when executed by a processor, implement the vehicle collision risk prediction method as provided in any embodiment of the present invention.

[0065] Fifthly, embodiments of the present invention provide a vehicle that includes a vehicle collision risk prediction device provided in any embodiment of the present invention, or a computer device provided in any embodiment of the present invention.

[0066] Sixthly, embodiments of the present invention provide a computer program, the computer program including program instructions, which, when executed by a computer, implement the vehicle collision risk prediction method provided in any embodiment of the present invention. Attached Figure Description

[0067] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0068] Figure 1a This is a schematic diagram of a driving scenario on a curved road provided in Embodiment 1 of the present invention;

[0069] Figure 1b This is a flowchart of a vehicle collision risk prediction method provided in Embodiment 1 of the present invention;

[0070] Figure 1c This is a schematic diagram of the trajectory of a vehicle traveling on a curved road and the trajectory of the grounding point of the roadside guardrail provided in Embodiment 1 of the present invention;

[0071] Figure 1d This is a schematic diagram of the electromagnetic wave travel on a curved road section provided in Embodiment 1 of the present invention;

[0072] Figure 2 This is a structural block diagram of a vehicle collision risk prediction device provided in Embodiment 2 of the present invention;

[0073] Figure 3 This is a structural block diagram of a computer device provided in Embodiment 3 of the present invention;

[0074] Figure 4 This is a schematic diagram of a vehicle provided in Embodiment 4 of the present invention. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] It should be noted that the terms "comprising" and "having," and any variations thereof, in the embodiments and drawings of this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0077] This invention discloses a method, apparatus, device, and medium for predicting vehicle collision risks. These are described in detail below.

[0078] Example 1

[0079] The method provided in this embodiment can be applied to scenarios where vehicles are traveling on curved road sections and there are roadside guardrails on the curves. Typically, it can be applied to ramp sections with large turning radii. Figure 1a This is a schematic diagram of a driving scenario on a curved road provided in Embodiment 1 of the present invention. Figure 1a As shown, the vehicle is traveling ahead of an obstacle vehicle or an oncoming vehicle occupying the current lane to change lanes and overtake. Due to the special nature of curved road sections, the vehicle cannot perceive the presence of obstacles ahead while driving on a curve. If the driver can see the obstacle (in a manual driving model), or if the vehicle detects an obstacle through its onboard sensors (in an autonomous driving model), and then applies emergency braking, there is a risk of collision due to insufficient braking distance. Therefore, the vehicle needs to determine whether there is an obstacle ahead while turning, i.e., beyond visual range, and predict the potential collision risk between the vehicle and the obstacle in advance. This allows for advance planning of corresponding driving strategies in case of collision risk, ensuring safety while driving on curves. The following is a detailed description of a vehicle collision risk prediction method provided in this embodiment.

[0080] Figure 1bThis is a flowchart illustrating a vehicle collision risk prediction method according to Embodiment 1 of the present invention. This method can be applied to in-vehicle terminals such as in-vehicle computers and industrial personal computers (IPCs), and can also be applied to servers; the present invention does not limit its application in this regard. The method provided in this embodiment can be executed by a vehicle collision risk prediction device, which can be implemented through software and / or hardware. Figure 1b As shown, the method provided in this embodiment specifically includes:

[0081] S110. When it is detected that the current vehicle is traveling on a curved road section, determine the radius of the current vehicle's travel trajectory.

[0082] Among these methods, the current vehicle's perception system can detect that the current road segment is a curved road segment, or the navigation map, such as a high-precision map, can be used to locate the current road segment as a curved road segment.

[0083] In this embodiment, the vehicle is currently traveling on a curved road section, and its travel trajectory is an arc, the radius of which is the turning radius of the vehicle. There are several ways to determine the turning radius of the vehicle. For example, the front wheel angle can be obtained from the steering wheel angle, and then the turning radius can be obtained from the front wheel angle based on the Ackermann steering geometry formula.

[0084] As another optional implementation, when determining the radius of the current vehicle's trajectory, the positional information of the vehicle's trajectory points can be used to fit each trajectory point to obtain the trajectory curve equation. Then, the radius of the vehicle's trajectory can be determined using this curve equation. Specifically, this can be achieved through the following steps a1 to c1:

[0085] a1. Determine the position information of the trajectory points of the current vehicle based on the vehicle coordinate system.

[0086] The vehicle coordinate system can be a coordinate system with the center point of the vehicle's front as the origin O, the x-axis parallel to the direction of the vehicle's front as the x-axis, and the y-axis perpendicular to the direction of the vehicle's front as the y-axis. Based on this vehicle coordinate system, the coordinate information of the current vehicle's trajectory points can be obtained.

[0087] b1. Fit each trajectory point according to its position information to obtain the equation of the driving trajectory curve.

[0088] Specifically, the curve equation used when fitting curves to each trajectory point can be an Nth-degree polynomial curve equation, specifically a quadratic curve or a cubic curve equation. This embodiment does not limit the specific form of the curve equation.

[0089] c1. Determine the radius of the current vehicle's trajectory based on the trajectory curve equation.

[0090] In this embodiment, determining the radius of the current vehicle's trajectory based on the trajectory curve equation can be achieved as follows: The curvature information of the trajectory curve equation is determined, and the radius of the current vehicle's trajectory is calculated based on the geometric relationship between the curvature information and the radius of curvature. Specifically, this can be expressed by the following formula:

[0091]

[0092] Where f1 represents the equation of the current vehicle's trajectory curve, K1 represents the curvature information of the trajectory curve equation, and R1 represents the radius of the current vehicle's trajectory.

[0093] Specifically, Figure 1c This is a schematic diagram of the vehicle's trajectory and the roadside guardrail's contact point trajectory on a curved road section, as provided in Embodiment 1 of the present invention. Figure 1c As shown, R1 is the radius of the current vehicle's trajectory, and R2 is the radius of the trajectory of the roadside guardrail's contact point; their centers are at the same location. The radius of the roadside guardrail's contact point (i.e., the radius of curvature of the roadside guardrail) can be obtained directly from the navigation map, or it can be calculated as described above. Specifically, this can be achieved through steps a2 to c2. The obtained radius of the roadside guardrail's contact point can be used in the calculation of the radius of curvature of subsequent potential collision objects.

[0094] a2. Determine the coordinate information of the roadside guardrail grounding point based on the vehicle coordinate system.

[0095] The coordinates of the roadside guardrail's contact point can be obtained through visual perception or high-precision map positioning. If the obtained coordinates of the roadside guardrail's contact point are not based on the vehicle's coordinate system, they can be transformed to the vehicle's coordinate system to obtain the coordinates of the roadside guardrail's contact point based on the vehicle's coordinate system.

[0096] b2. Fit the coordinate information of each roadside guardrail grounding point based on the Nth degree polynomial to obtain the trajectory equation of the roadside guardrail grounding point.

[0097] There are various curve equations used when fitting the grounding point of the roadside guardrail, such as quadratic curve equations and cubic curve equations. This embodiment does not limit the specific form of the curve equation.

[0098] c2. Determine the curvature information of the trajectory equation of the roadside guardrail's contact point, and calculate the radius of curvature of the roadside guardrail based on the geometric relationship between the curvature information and the radius of curvature, i.e., the reciprocal relationship between the curvature information and the radius of curvature. This can be achieved through the following formula:

[0099]

[0100] Where f2 represents the trajectory equation of the roadside guardrail grounding point, K2 represents the curvature information of the trajectory equation of the roadside guardrail grounding point, and R2 represents the radius of curvature of the roadside guardrail grounding point.

[0101] S120. Based on the number of radar electromagnetic wave echoes received successively, if it is determined that there is a potential collision object in front of the current vehicle, determine the radius of curvature of the trajectory of the potential collision object on the curved road section.

[0102] The potential collision obstacle can be an obstacle vehicle in front of the current vehicle, an oncoming vehicle changing lanes to overtake, or other obstacles. Because the current vehicle cannot perceive obstacles far ahead when driving on a curved road, it is prone to collisions. In this embodiment, the secondary reflection principle of electromagnetic waves emitted by the vehicle-mounted radar can be used to determine in advance whether there is a potential collision obstacle ahead of the turn, even in beyond visual range.

[0103] Those skilled in the art will understand that when a vehicle is traveling on a curved road section, and there is a roadside guardrail on the curve, the electromagnetic waves emitted by the vehicle radar will be reflected back along the direction of emission after reaching a certain point on the roadside guardrail. That is, the vehicle will receive the electromagnetic wave echo. In addition, at the point of reflection, the electromagnetic wave will be emitted again in another direction. Figure 1d This is a schematic diagram of the electromagnetic wave travel on a curved road section provided in Embodiment 1 of the present invention. Figure 1d As shown, the electromagnetic waves emitted by the vehicle's radar will be reflected back into the vehicle after reaching point A on the roadside guardrail, with a transmission distance of 2L1. Furthermore, the electromagnetic waves will be re-emitted along the L2 direction at point A on the roadside guardrail. If there are no other vehicles or obstacles in front of the vehicle on this curved section of road, the electromagnetic waves re-emitted from point A will not undergo a second reflection; that is, the vehicle will only receive the electromagnetic wave echo reflected back from point A once. If there are other vehicles or obstacles B in front of the vehicle on this curved section of road, the electromagnetic waves, after reaching point A, will be emitted from point A to point B, and then reflected back to point A from point B, and then reflected back to the vehicle from point A again. In other words, in addition to receiving the first electromagnetic wave echo reflected from point A, the vehicle will also receive a second electromagnetic wave echo reflected from the potential collision point. Therefore, the transmission distance of the second electromagnetic wave echo received after the vehicle's radar emits the electromagnetic waves is 2(L1+L2). The transmission distance of the electromagnetic wave from reflection point A to the object at risk of collision and then back to reflection point A is 2L2.

[0104] In this embodiment, the radius of curvature of the potential collision object on the curved road section can be determined through the following steps 1-2:

[0105] 1. Based on the first time difference from the start of the electromagnetic wave emitted by the vehicle radar to the first receipt of the electromagnetic wave echo, and the second time difference from the second receipt of the electromagnetic wave echo, calculate the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the object at risk of collision.

[0106] The first electromagnetic wave echo received by the vehicle is reflected from a target point on the roadside guardrail, for example... Figure 1d The electromagnetic wave echo reflected at point A is shown. The electromagnetic wave is emitted from the vehicle's onboard radar, reaches the reflection point A on the roadside guardrail, and then reflects back to the vehicle. The first time difference is Δt1. The transmission distance of the electromagnetic wave from the vehicle to the roadside guardrail reflection point is... Where v is the speed of light.

[0107] The second time the vehicle receives the electromagnetic wave echo is when the electromagnetic wave, emitted from the vehicle's onboard radar, first reaches reflection point A on the roadside guardrail, then reflects from point A to the potential collision obstacle B, which then reflects the electromagnetic wave back to reflection point A on the roadside guardrail, and finally back to the vehicle. The time difference between the emission of the electromagnetic wave from the onboard radar and the second reception is Δt2, and the transmission distance of the electromagnetic wave is 2(L1+L2)=Δt2*v, that is...

[0108] In summary, the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the potential collision object can be obtained as follows:

[0109] 2. Based on the trigonometric function relationship between the reflection distance, the radius of curvature of the trajectory of the potential collision object on the curved road section, and the radius of curvature of the roadside guardrail, calculate the radius of curvature of the trajectory of the potential collision object on the curved road section.

[0110] like Figure 1d As shown, the trajectory of the object at risk of collision can form the three sides of a two-dimensional planar triangle by the line segment containing the radius of curvature R3 of the curved road section, the line segment containing the radius of curvature R2 of the roadside guardrail, and the line segment containing the reflection distance L2 from the target reflection point of the roadside guardrail to the object at risk of collision. The three sides satisfy the trigonometric function relationship between the three sides of the triangle.

[0111] Specifically, the radius of curvature of the trajectory of a potential collision object on a curved road segment can be calculated as follows:

[0112] Based on the sine theorem, the angle between the first line segment from the potential collision object to the target reflection point and the second line segment from the target reflection point to the center of curvature of the roadside guardrail is calculated. Then, based on the cosine theorem, and using the calculated angle, reflection distance, and the radius of curvature of the roadside guardrail, the radius of curvature of the potential collision object's trajectory on the curved road section is calculated. This can be expressed by the following formula:

[0113] like Figure 1d As shown, based on the law of sines, we can obtain:

[0114]

[0115] Based on this, we can obtain Where β is the angle between the first line segment and the second line segment, the first line segment is the line connecting the object at risk of collision to the target reflection point, the second line segment is the line connecting the target reflection point to the center of the curvature circle of the roadside guardrail, and α represents the angle between the line connecting the target reflection point and the origin of the vehicle coordinate system and the x-axis of the vehicle coordinate system.

[0116] like Figure 1d As shown, the three sides of a triangle are formed by the line segment containing the reflection distance L2, the line segment containing the radius of curvature R2 of the roadside guardrail, and the line segment containing the radius of curvature R3 of the trajectory of the potential collision object on the curved road section. Based on the law of cosines, we can obtain:

[0117]

[0118] Therefore, the radius of curvature of the trajectory of the potential collision object on the curved road section can be obtained as follows:

[0119]

[0120] S130. Calculate the difference between the radius of the driving trajectory and the radius of curvature of the trajectory of the risky collision object on the curved road section, and predict the collision risk between the current vehicle and the risky collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

[0121] In this embodiment, if the absolute value of the difference is greater than or equal to the width of the lane where the current vehicle is located, it is determined that there is no collision risk between the current vehicle and the potential collision object; if the absolute value of the difference is less than the width of the lane where the current vehicle is located, it is determined that there is a collision risk between the current vehicle and the potential collision object. Figure 1d As shown, if |R1-R3|≥h, there is no risk of collision between the current vehicle and the object of collision; if |R1-R3|<h, there is a risk of collision between the current vehicle and the object of collision. h represents the width of the lane where the current vehicle is located.

[0122] Furthermore, after determining that there is a collision risk between the current vehicle and the potential collision object, the vehicle can be slowed down to reduce the collision risk. Alternatively, in manual driving mode, the vehicle can be controlled to issue an alarm to remind the driver to pay attention to safety.

[0123] The technical solution provided in this embodiment, when a vehicle is traveling on a curved road, utilizes the principle of secondary reflection of radar waves to determine the presence of a potential collision obstacle ahead of the vehicle in a beyond-visual-range situation. Based on the relationship between the absolute value of the difference between the vehicle's trajectory radius and the radius of curvature of the potential collision obstacle on the curved road section, and the width of the lane currently occupied by the vehicle, it is possible to predict whether a collision risk exists between the vehicle and the potential collision obstacle. This allows for advance deceleration or braking in case of a collision risk, thus avoiding the collision and ensuring safety when driving on a curved road.

[0124] Example 2

[0125] Figure 2 This is a structural block diagram of a vehicle collision risk prediction device provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the device includes: a vehicle driving radius determination module 210, a collision risk object trajectory radius determination module 220, and a collision risk prediction module 230, wherein,

[0126] The vehicle driving radius determination module 210 is configured to determine the driving trajectory radius of the current vehicle when it is detected that the current vehicle is driving on a curved road section;

[0127] The collision risk object trajectory radius determination module 220 is configured to determine the radius of curvature of the trajectory of the risk object on a curved road section based on the number of radar electromagnetic wave echoes received successively, when it is determined that there is a risk collision object in front of the current vehicle. The radius of the current vehicle's trajectory is the same as the center position of the circle corresponding to the radius of curvature of the risk collision object's trajectory on the curved road section.

[0128] The collision risk prediction module 230 is configured to calculate the difference between the radius of the driving trajectory and the radius of curvature of the risk collision object on the curved road section, and predict the collision risk between the current vehicle and the risk collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

[0129] The vehicle driving radius determination module includes:

[0130] The trajectory point location determination unit is configured to determine the trajectory point location information of the current vehicle based on the vehicle coordinate system;

[0131] The driving trajectory curve fitting unit is configured to fit each trajectory point according to the position information of each trajectory point to obtain the driving trajectory curve equation;

[0132] The trajectory radius determination unit is configured to determine the current vehicle's trajectory radius based on the trajectory curve equation.

[0133] Optionally, the driving trajectory curve fitting unit is specifically configured as follows:

[0134] The equation of the current vehicle's driving trajectory curve is obtained by fitting each trajectory point with an Nth-order polynomial.

[0135] Accordingly, the driving trajectory radius determination unit is specifically configured as follows:

[0136] Determine the curvature information of the driving trajectory curve equation, and calculate the current vehicle's driving trajectory radius based on the geometric relationship between the curvature information and the radius of curvature.

[0137] Optional, the collision risk object trajectory radius determination module includes:

[0138] The reflection distance calculation unit is configured to calculate the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the object at risk of collision, based on the first time difference from the first time the radar emits electromagnetic waves to the first time the radar electromagnetic wave echo is received, and the second time difference from the second time the electromagnetic wave echo is received.

[0139] The collision risk object curvature radius determination unit is configured to calculate the radius of curvature of the collision risk object's trajectory on the curved road section based on the trigonometric function relationship between the reflection distance, the radius of curvature of the collision risk object's trajectory on the curved road section, and the radius of curvature of the roadside guardrail.

[0140] Optionally, the radius of curvature of the roadside guardrail is calculated as follows:

[0141] The grounding point of the roadside guardrail is determined based on the coordinate information of the vehicle coordinate system;

[0142] The coordinate information of each roadside guardrail grounding point is fitted based on an Nth-order polynomial to obtain the trajectory equation of the roadside guardrail grounding point.

[0143] The curvature information of the trajectory equation of the roadside guardrail's ground contact point is determined, and the curvature radius of the roadside guardrail is calculated based on the geometric relationship between the curvature information and the curvature radius, wherein the curvature radius of the roadside guardrail is at the same center position as the radius of the driving trajectory.

[0144] Optionally, the collision risk object curvature radius determination unit is specifically configured as follows:

[0145] Based on the sine theorem, calculate the angle between the first line segment from the risk collision object to the target reflection point and the second line segment from the target reflection point to the center of the curvature circle of the roadside guardrail;

[0146] Based on the law of cosines, and according to the angle between the first and second line segments, the reflection distance, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated.

[0147] Optional, the collision risk prediction module is specifically configured as follows:

[0148] If the absolute value of the difference is greater than or equal to the width of the lane where the current vehicle is located, then it is determined that there is no risk of collision between the current vehicle and the object of potential collision.

[0149] If the absolute value of the difference is less than the width of the lane where the current vehicle is located, then it is determined that there is a collision risk between the current vehicle and the object at risk of collision.

[0150] Optionally, the apparatus provided in this embodiment of the invention further includes:

[0151] After determining that there is a collision risk between the current vehicle and the potential collision object, the current vehicle is controlled to slow down.

[0152] The vehicle collision risk prediction device provided in this embodiment of the invention can execute the vehicle collision risk prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in the above embodiments can be found in the vehicle collision risk prediction method provided in any embodiment of the invention.

[0153] Example 3

[0154] Figure 3 This is a structural block diagram of a computer device provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the computer device includes:

[0155] At least one processor Figure 3 The image shows a processor 520.

[0156] The processor 520 is coupled to the memory 510, which stores a program or instructions that run on the processor 520. When the program or instructions are executed by the processor 520, they implement the vehicle collision risk prediction method provided in any embodiment of the present invention.

[0157] Based on the above embodiments, another embodiment of the present invention provides a vehicle that includes the apparatus as described in any of the above embodiments, or includes the computer equipment as described above.

[0158] Example 4

[0159] Figure 4 This is a schematic diagram of a vehicle provided in Embodiment 4 of the present invention. Figure 4As shown, the vehicle includes a speed sensor 61, an ECU (Electronic Control Unit) 62, a GPS (Global Positioning System) positioning device 63, and a T-Box (Telematics Box) 64. The speed sensor 61 measures the vehicle speed and uses this speed as an empirical speed for model training; the GPS positioning device 63 obtains the vehicle's current geographical location; the T-Box 64 can act as a gateway to communicate with the server; and the ECU 62 can execute the aforementioned vehicle collision risk prediction method.

[0160] In addition, the vehicle may also include: a V2X (Vehicle-to-Everything) module 65, a radar 66, and a camera 67. The V2X module 65 is used to communicate with other vehicles, roadside equipment, etc.; the radar 66 or camera 67 is used to perceive road environment information in front and / or other directions to obtain raw point cloud data; the radar 66 and / or camera 67 can be configured at the front and / or rear of the vehicle.

[0161] Based on the above method embodiments, another embodiment of the present invention provides a readable storage medium having a program or instructions stored thereon, which, when executed by a processor, causes the processor to implement the vehicle collision risk prediction method as described in any of the above embodiments.

[0162] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing the present invention.

[0163] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for predicting vehicle collision risk, characterized in that, include: When the current vehicle is detected to be traveling on a curved road section, determine the radius of the current vehicle's travel trajectory; Based on the number of radar electromagnetic wave echoes received successively, if it is determined that there is a potential collision object in front of the current vehicle, the radius of curvature of the trajectory of the potential collision object in the curved road section is determined. In the case of receiving two radar electromagnetic wave echoes successively, the existence of the potential collision object is determined. The second radar electromagnetic wave echo received is the echo of the electromagnetic wave reflected by the potential collision object and then reflected back by the roadside guardrail. The radius of the driving trajectory is at the same center position as the radius of curvature. The difference between the radius of the driving trajectory and the radius of curvature of the trajectory of the potential collision object in the curved road section is calculated, and the collision risk between the current vehicle and the potential collision object is predicted based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

2. The method according to claim 1, characterized in that, Determining the radius of the current vehicle's trajectory includes: Determine the current vehicle's trajectory point position information based on its own coordinate system; Based on the location information of each trajectory point, the equation of the driving trajectory curve is obtained by fitting each trajectory point. The radius of the current vehicle's trajectory is determined based on the equation of the driving trajectory curve.

3. The method according to claim 2, characterized in that, The process of fitting the trajectory points according to their location information to obtain the driving trajectory curve equation includes: The equation of the current vehicle's driving trajectory curve is obtained by fitting each trajectory point with an Nth-degree polynomial. Accordingly, determining the radius of the current vehicle's trajectory based on the trajectory curve equation includes: The curvature information of the driving trajectory curve equation is determined, and the driving trajectory radius of the current vehicle is calculated based on the geometric relationship between the curvature information and the radius of curvature.

4. The method according to claim 1, characterized in that, Determining the radius of curvature of the trajectory of the potential collision object on the curved road segment includes: Based on the first time difference from when the vehicle-mounted radar emits electromagnetic waves to when it first receives the radar electromagnetic wave echo, and the second time difference from when it receives the electromagnetic wave echo for the second time, the reflection distance of the electromagnetic wave emitted by the radar from the target reflection point of the roadside guardrail to the object at risk of collision is calculated. Based on the trigonometric function relationship between the reflection distance, the radius of curvature of the trajectory of the potential collision object in the curved road section, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object in the curved road section is calculated.

5. The method according to claim 4, characterized in that, The radius of curvature of the roadside guardrail is calculated as follows: The grounding point of the roadside guardrail is determined based on the coordinate information of the vehicle coordinate system; The coordinate information of each roadside guardrail grounding point is fitted based on an Nth-order polynomial to obtain the trajectory equation of the roadside guardrail grounding point. The curvature information of the trajectory equation of the grounding point of the roadside guardrail is determined, and the curvature radius of the roadside guardrail is calculated based on the geometric relationship between the curvature information and the curvature radius, wherein the curvature radius of the roadside guardrail is at the same center position as the radius of the driving trajectory.

6. The method according to claim 4, characterized in that, Based on the trigonometric relationship between the reflection distance, the radius of curvature of the trajectory of the potential collision object on the curved road section, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated, including: Based on the sine theorem, calculate the angle between the first line segment from the risk collision object to the target reflection point and the second line segment from the target reflection point to the center of the curvature circle of the roadside guardrail; Based on the law of cosines, and according to the angle between the first line segment and the second line segment, the reflection distance, and the radius of curvature of the roadside guardrail, the radius of curvature of the trajectory of the potential collision object on the curved road section is calculated.

7. The method according to claim 1, characterized in that, The step of predicting the collision risk between the current vehicle and the potential collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located includes: If the absolute value of the difference is greater than or equal to the width of the lane where the current vehicle is located, then it is determined that there is no risk of collision between the current vehicle and the object of collision. If the absolute value of the difference is less than the width of the lane where the current vehicle is located, then it is determined that there is a collision risk between the current vehicle and the risky collision object.

8. A vehicle collision risk prediction device, characterized in that, include: The vehicle driving radius determination module is configured to determine the driving trajectory radius of the current vehicle when it is detected that the current vehicle is driving on a curved road section; The collision risk object trajectory radius determination module is configured to determine the radius of curvature of the trajectory of the risk object on the curved road section based on the number of radar electromagnetic wave echoes received successively. Specifically, if the presence of the risk object is determined when two radar electromagnetic wave echoes are received successively, the second radar electromagnetic wave echo is an echo that is reflected back by the roadside guardrail after being reflected by the risk object. The trajectory radius and the center position of the circle corresponding to the radius of curvature are the same. The collision risk prediction module is configured to calculate the difference between the radius of the driving trajectory and the radius of curvature of the trajectory of the potential collision object on the curved road segment, and predict the collision risk between the current vehicle and the potential collision object based on the relationship between the absolute value of the difference and the width of the lane where the current vehicle is located.

9. A computer device, characterized in that, It includes at least one processor coupled to a memory, the memory storing a program or instructions that run on the processor, the program or instructions which, when executed by the processor, implement the steps of the vehicle collision risk prediction method as described in any one of claims 1 to 6.

10. A readable storage medium having a program or instructions stored thereon, characterized in that, When the program or instructions are executed by the processor, they implement the steps of the vehicle collision risk prediction method as described in any one of claims 1 to 6.

Images